Merge da90df06c3 into 1036478d13

* WEB URLs are, MWEB not
* resolves #33017

youtube_dl/extractor/doodstream.py

@@ -0,0 +1,132 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from random import choice as random_choice
+from string import ascii_letters, digits
+from time import time as time_time
+
+from ..compat import compat_filter as filter
+from ..utils import (
+    clean_html,
+    ExtractorError,
+    get_element_by_class,
+    parse_duration,
+    parse_filesize,
+    update_url_query,
+    unified_strdate,
+    url_or_none,
+)
+
+from .common import InfoExtractor
+
+
+class DoodStreamIE(InfoExtractor):
+    # dood.* redirects
+    # .watch -> .re (but HEAD request fails in GenericIE)
+    # .so -> .li
+    _VALID_URL = r'https?://(?:www\.)?(?P<host>dood\.(?:to|la|li|pm|re|sh|watch|ws|one)|ds2play\.com)/[ed]/(?P<id>[a-z\d]+)'
+    _TESTS = [{
+        'url': 'https://dood.li/e/h7ecgw5oqn8k',
+        'md5': '90f2af170551c17fc78bee7426890054',
+        'info_dict': {
+            'id': 'h7ecgw5oqn8k',
+            'ext': 'mp4',
+            'title': 'Free-Slow-Music',
+            'upload_date': '20230814',
+            'thumbnail': 'https://img.doodcdn.co/splash/7mbnwydhb6kb7xyk.jpg',
+        },
+    }, {
+        'url': 'https://dood.to/d/is34uy8wvaet',
+        'md5': '04740d3ba93bcd638aa7a097d9226710',
+        'info_dict': {
+            'id': 'is34uy8wvaet',
+            'ext': 'mp4',
+            'title': 'Akhanda (2021) Telugu DVDScr MP3 700MB',
+            'upload_date': '20211202',
+            'thumbnail': r're:https?://img\.doodcdn\.com?/[\w/]+\.jpg',
+            'filesize_approx': int,
+            'duration': 9886,
+        },
+        'skip': 'Video not found',
+    }, {
+        'url': 'https://dood.sh/d/wlihoael8uog',
+        'md5': '2c14444c89788cc309738c1560abe278',
+        'info_dict': {
+            'id': 'wlihoael8uog',
+            'ext': 'mp4',
+            'title': 'VID 20220319 161659',
+            'thumbnail': r're:https?://img\.doodcdn\.com?/splash/rmpnhb8ckkk79cge\.jpg',
+            'upload_date': '20220319',
+            'filesize_approx': int,
+            'duration': 12.0,
+        },
+    }, {
+        'url': 'http://dood.ws/d/h7ecgw5oqn8k',
+        'only_matching': True,
+    }, {
+        'url': 'https://dood.li/d/wlihoael8uog',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        host = 'dood.li'
+        url = 'https://%s/e/%s' % (host, video_id)
+        webpage = self._download_webpage(url, video_id, note='Downloading "/e/" webpage')
+
+        def get_title(html, fatal=False):
+            return self._html_search_regex(r'<title\b[^>]*>([^<]+?)(?:[|-]\s+DoodStream\s*)?</title', html, 'title', fatal=fatal)
+
+        title = get_title(webpage)
+        if title == 'Video not found' or (
+                title == '' and 'Not Found' == self._html_search_regex(r'<h1\b[^>]*>([^<]+?)</h1', webpage, 'heading1', default=None)):
+            raise ExtractorError(title, expected=True)
+
+        pass_md5, token = self._search_regex(
+            r'["\']/(?P<pm>pass_md5/[\da-f-]+/(?P<tok>[\da-z]+))', webpage, 'tokens',
+            group=('pm', 'tok'))
+        headers = {
+            'Referer': url,
+        }
+        # construct the media link
+        final_url = self._download_webpage(
+            'https://%s/%s' % (host, pass_md5), video_id, headers={
+                'Referer': url,
+            }, note='Downloading authpage URL')
+        final_url += ''.join((random_choice(ascii_letters + digits)
+                              for _ in range(10)))
+        final_url = update_url_query(final_url, {
+            'token': token,
+            'expiry': int(time_time() * 1000),
+        })
+
+        # get additional metadata
+        thumb = next(filter(None, (url_or_none(self._html_search_meta(x, webpage, default=None))
+                                   for x in ('og:image', 'twitter:image'))), None)
+        description = self._html_search_meta(
+            ('og:description', 'description', 'twitter:description'), webpage, default=None)
+
+        webpage = self._download_webpage(
+            'https://%s/d/%s' % (host, video_id), video_id, fatal=False,
+            note='Downloading alternative "/d/" page') or ''
+
+        title = (
+            self._html_search_meta(('og:title', 'twitter:title'), webpage, default=None)
+            or get_title(webpage, fatal=(title is not None))
+            or title)
+
+        def get_class_text(x):
+            return clean_html(get_element_by_class(x, webpage))
+
+        return {
+            'id': video_id,
+            'title': title,
+            'url': final_url,
+            'http_headers': headers,
+            'ext': 'mp4',
+            'upload_date': unified_strdate(get_class_text('uploadate')),
+            'duration': parse_duration(get_class_text('length')),
+            'filesize_approx': parse_filesize(get_class_text('size')),
+            'description': description,
+            'thumbnail': thumb,
+        }

youtube_dl/extractor/extractors.py

@@ -304,6 +304,7 @@ from .dlf import (
 from .dfb import DFBIE
 from .dhm import DHMIE
 from .digg import DiggIE
+from .doodstream import DoodStreamIE
 from .dotsub import DotsubIE
 from .douyutv import (
     DouyuShowIE,

youtube_dl/extractor/youtube.py

@@ -9,6 +9,7 @@ import json
 import os.path
 import random
 import re
+import string
 import time
 import traceback
 
@@ -67,6 +68,7 @@ from ..utils import (
 
 class YoutubeBaseInfoExtractor(InfoExtractor):
     """Provide base functions for Youtube extractors"""
+
     _LOGIN_URL = 'https://accounts.google.com/ServiceLogin'
     _TWOFACTOR_URL = 'https://accounts.google.com/signin/challenge'
 
@@ -138,7 +140,7 @@ class YoutubeBaseInfoExtractor(InfoExtractor):
                 [2, 1, None, 1,
                  'https://accounts.google.com/ServiceLogin?passive=true&continue=https%3A%2F%2Fwww.youtube.com%2Fsignin%3Fnext%3D%252F%26action_handle_signin%3Dtrue%26hl%3Den%26app%3Ddesktop%26feature%3Dsign_in_button&hl=en&service=youtube&uilel=3&requestPath=%2FServiceLogin&Page=PasswordSeparationSignIn',
                  None, [], 4],
-                1, [None, None, []], None, None, None, True
+                1, [None, None, []], None, None, None, True,
             ],
             username,
         ]
@@ -160,7 +162,7 @@ class YoutubeBaseInfoExtractor(InfoExtractor):
             None, 1, None, [1, None, None, None, [password, None, True]],
             [
                 None, None, [2, 1, None, 1, 'https://accounts.google.com/ServiceLogin?passive=true&continue=https%3A%2F%2Fwww.youtube.com%2Fsignin%3Fnext%3D%252F%26action_handle_signin%3Dtrue%26hl%3Den%26app%3Ddesktop%26feature%3Dsign_in_button&hl=en&service=youtube&uilel=3&requestPath=%2FServiceLogin&Page=PasswordSeparationSignIn', None, [], 4],
-                1, [None, None, []], None, None, None, True
+                1, [None, None, []], None, None, None, True,
             ]]
 
         challenge_results = req(
@@ -213,7 +215,7 @@ class YoutubeBaseInfoExtractor(InfoExtractor):
                     user_hash, None, 2, None,
                     [
                         9, None, None, None, None, None, None, None,
-                        [None, tfa_code, True, 2]
+                        [None, tfa_code, True, 2],
                     ]]
 
                 tfa_results = req(
@@ -284,7 +286,7 @@ class YoutubeBaseInfoExtractor(InfoExtractor):
             'client': {
                 'clientName': 'WEB',
                 'clientVersion': '2.20201021.03.00',
-            }
+            },
         },
     }
 
@@ -385,7 +387,7 @@ class YoutubeBaseInfoExtractor(InfoExtractor):
                 'client': {
                     'clientName': 'WEB',
                     'clientVersion': '2.20201021.03.00',
-                }
+                },
             },
             'query': query,
         }
@@ -462,7 +464,7 @@ class YoutubeBaseInfoExtractor(InfoExtractor):
             #       (HTML, videodetails, metadata, renderers)
             'name': ('content', 'author', (('ownerChannelName', None), 'title'), ['text']),
             'url': ('href', 'ownerProfileUrl', 'vanityChannelUrl',
-                    ['navigationEndpoint', 'browseEndpoint', 'canonicalBaseUrl'])
+                    ['navigationEndpoint', 'browseEndpoint', 'canonicalBaseUrl']),
         }
         if any((videodetails, metadata, renderers)):
             result = (
@@ -671,7 +673,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/8KVIDEO',
                 'description': '',
                 'uploader': '8KVIDEO',
-                'title': 'UHDTV TEST 8K VIDEO.mp4'
+                'title': 'UHDTV TEST 8K VIDEO.mp4',
             },
             'params': {
                 'youtube_include_dash_manifest': True,
@@ -711,7 +713,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'uploader_url': r're:https?://(?:www\.)?youtube\.com/@theamazingatheist',
                 'title': 'Burning Everyone\'s Koran',
                 'description': 'SUBSCRIBE: http://www.youtube.com/saturninefilms \r\n\r\nEven Obama has taken a stand against freedom on this issue: http://www.huffingtonpost.com/2010/09/09/obama-gma-interview-quran_n_710282.html',
-            }
+            },
         },
         # Age-gated videos
         {
@@ -839,7 +841,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
             },
             'expected_warnings': [
                 'DASH manifest missing',
-            ]
+            ],
         },
         # Olympics (https://github.com/ytdl-org/youtube-dl/issues/4431)
         {
@@ -1820,8 +1822,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
 
         # cpn generation algorithm is reverse engineered from base.js.
         # In fact it works even with dummy cpn.
-        CPN_ALPHABET = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789-_'
+        CPN_ALPHABET = string.ascii_letters + string.digits + '-_'
-        cpn = ''.join(CPN_ALPHABET[random.randint(0, 256) & 63] for _ in range(0, 16))
+        cpn = ''.join(CPN_ALPHABET[random.randint(0, 256) & 63] for _ in range(16))
 
         # more consistent results setting it to right before the end
         qs = parse_qs(playback_url)
@@ -1881,8 +1883,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
         mobj = re.match(cls._VALID_URL, url, re.VERBOSE)
         if mobj is None:
             raise ExtractorError('Invalid URL: %s' % url)
-        video_id = mobj.group(2)
+        return mobj.group(2)
-        return video_id
 
     def _extract_chapters_from_json(self, data, video_id, duration):
         chapters_list = try_get(
@@ -2035,7 +2036,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
             headers = {
                 'X-YouTube-Client-Name': '85',
                 'X-YouTube-Client-Version': '2.0',
-                'Origin': 'https://www.youtube.com'
+                'Origin': 'https://www.youtube.com',
             }
 
             video_info = self._call_api('player', query, video_id, fatal=False, headers=headers)
@@ -2064,8 +2065,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
             return ''.join([r['text'] for r in runs if isinstance(r.get('text'), compat_str)])
 
         search_meta = (
-            lambda x: self._html_search_meta(x, webpage, default=None)) \
+            (lambda x: self._html_search_meta(x, webpage, default=None))
-            if webpage else lambda x: None
+            if webpage else lambda _: None)
 
         video_details = player_response.get('videoDetails') or {}
         microformat = try_get(
@@ -2137,7 +2138,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
         def build_fragments(f):
             return LazyList({
                 'url': update_url_query(f['url'], {
-                    'range': '{0}-{1}'.format(range_start, min(range_start + CHUNK_SIZE - 1, f['filesize']))
+                    'range': '{0}-{1}'.format(range_start, min(range_start + CHUNK_SIZE - 1, f['filesize'])),
                 })
             } for range_start in range(0, f['filesize'], CHUNK_SIZE))
 
@@ -2236,7 +2237,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                     'protocol': 'http_dash_segments',
                     'fragments': build_fragments(dct),
                 } if dct['filesize'] else {
-                    'downloader_options': {'http_chunk_size': CHUNK_SIZE}  # No longer useful?
+                    'downloader_options': {'http_chunk_size': CHUNK_SIZE},  # No longer useful?
                 })
 
             formats.append(dct)
@@ -2414,9 +2415,9 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
             'is_live': is_live,
         }
 
-        pctr = try_get(
+        pctr = traverse_obj(
             player_response,
-            lambda x: x['captions']['playerCaptionsTracklistRenderer'], dict)
+            ('captions', 'playerCaptionsTracklistRenderer', T(dict)))
         if pctr:
             def process_language(container, base_url, lang_code, query):
                 lang_subs = []
@@ -2430,31 +2431,34 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                     })
                 container[lang_code] = lang_subs
 
-            subtitles = {}
+            def process_subtitles():
-            for caption_track in (pctr.get('captionTracks') or []):
+                subtitles = {}
-                base_url = caption_track.get('baseUrl')
+                for caption_track in traverse_obj(pctr, (
-                if not base_url:
+                        'captionTracks', lambda _, v: v.get('baseUrl'))):
-                    continue
+                    base_url = self._yt_urljoin(caption_track['baseUrl'])
-                if caption_track.get('kind') != 'asr':
+                    if not base_url:
-                    lang_code = caption_track.get('languageCode')
-                    if not lang_code:
                         continue
-                    process_language(
+                    if caption_track.get('kind') != 'asr':
-                        subtitles, base_url, lang_code, {})
+                        lang_code = caption_track.get('languageCode')
-                    continue
+                        if not lang_code:
-                automatic_captions = {}
+                            continue
-                for translation_language in (pctr.get('translationLanguages') or []):
+                        process_language(
-                    translation_language_code = translation_language.get('languageCode')
+                            subtitles, base_url, lang_code, {})
-                    if not translation_language_code:
                         continue
-                    process_language(
+                    automatic_captions = {}
-                        automatic_captions, base_url, translation_language_code,
+                    for translation_language in traverse_obj(pctr, (
-                        {'tlang': translation_language_code})
+                            'translationLanguages', lambda _, v: v.get('languageCode'))):
-                info['automatic_captions'] = automatic_captions
+                        translation_language_code = translation_language['languageCode']
-            info['subtitles'] = subtitles
+                        process_language(
+                            automatic_captions, base_url, translation_language_code,
+                            {'tlang': translation_language_code})
+                    info['automatic_captions'] = automatic_captions
+                info['subtitles'] = subtitles
+
+            process_subtitles()
 
         parsed_url = compat_urllib_parse_urlparse(url)
-        for component in [parsed_url.fragment, parsed_url.query]:
+        for component in (parsed_url.fragment, parsed_url.query):
             query = compat_parse_qs(component)
             for k, v in query.items():
                 for d_k, s_ks in [('start', ('start', 't')), ('end', ('end',))]:
@@ -2684,7 +2688,7 @@ class YoutubeTabIE(YoutubeBaseInfoExtractor):
             'title': 'Super Cooper Shorts - Shorts',
             'uploader': 'Super Cooper Shorts',
             'uploader_id': '@SuperCooperShorts',
-        }
+        },
     }, {
         # Channel that does not have a Shorts tab. Test should just download videos on Home tab instead
         'url': 'https://www.youtube.com/@emergencyawesome/shorts',
@@ -2738,7 +2742,7 @@ class YoutubeTabIE(YoutubeBaseInfoExtractor):
             'description': 'md5:609399d937ea957b0f53cbffb747a14c',
             'uploader': 'ThirstForScience',
             'uploader_id': '@ThirstForScience',
-        }
+        },
     }, {
         'url': 'https://www.youtube.com/c/ChristophLaimer/playlists',
         'only_matching': True,
@@ -3037,7 +3041,7 @@ class YoutubeTabIE(YoutubeBaseInfoExtractor):
             'uploader': '3Blue1Brown',
             'uploader_id': '@3blue1brown',
             'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
-        }
+        },
     }]
 
     @classmethod
@@ -3335,7 +3339,7 @@ class YoutubeTabIE(YoutubeBaseInfoExtractor):
             'client': {
                 'clientName': 'WEB',
                 'clientVersion': client_version,
-            }
+            },
         }
         visitor_data = try_get(context, lambda x: x['client']['visitorData'], compat_str)
 
@@ -3354,7 +3358,7 @@ class YoutubeTabIE(YoutubeBaseInfoExtractor):
                 headers['x-goog-visitor-id'] = visitor_data
             data['continuation'] = continuation['continuation']
             data['clickTracking'] = {
-                'clickTrackingParams': continuation['itct']
+                'clickTrackingParams': continuation['itct'],
             }
             count = 0
             retries = 3
@@ -3613,7 +3617,7 @@ class YoutubePlaylistIE(InfoExtractor):
             'uploader': 'milan',
             'uploader_id': '@milan5503',
             'channel_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
-        }
+        },
     }, {
         'url': 'http://www.youtube.com/embed/_xDOZElKyNU?list=PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
         'playlist_mincount': 455,
@@ -3623,7 +3627,7 @@ class YoutubePlaylistIE(InfoExtractor):
             'uploader': 'LBK',
             'uploader_id': '@music_king',
             'channel_id': 'UC21nz3_MesPLqtDqwdvnoxA',
-        }
+        },
     }, {
         'url': 'TLGGrESM50VT6acwMjAyMjAxNw',
         'only_matching': True,
@@ -3734,7 +3738,7 @@ class YoutubeSearchIE(SearchInfoExtractor, YoutubeBaseInfoExtractor):
         'info_dict': {
             'id': 'youtube-dl test video',
             'title': 'youtube-dl test video',
-        }
+        },
     }]
 
     def _get_n_results(self, query, n):
@@ -3754,7 +3758,7 @@ class YoutubeSearchDateIE(YoutubeSearchIE):
         'info_dict': {
             'id': 'youtube-dl test video',
             'title': 'youtube-dl test video',
-        }
+        },
     }]
 
 
@@ -3769,7 +3773,7 @@ class YoutubeSearchURLIE(YoutubeBaseInfoExtractor):
             'id': 'youtube-dl test video',
             'title': 'youtube-dl test video',
         },
-        'params': {'playlistend': 5}
+        'params': {'playlistend': 5},
     }, {
         'url': 'https://www.youtube.com/results?q=test&sp=EgQIBBgB',
         'only_matching': True,
@@ -3785,6 +3789,7 @@ class YoutubeSearchURLIE(YoutubeBaseInfoExtractor):
 class YoutubeFeedsInfoExtractor(YoutubeTabIE):
     """
     Base class for feed extractors
+
     Subclasses must define the _FEED_NAME property.
     """
     _LOGIN_REQUIRED = True